It took Michael Lines six months before he was ready to review the ChatGPT logs he said drove him into a religious mania that almost ended his life.

In July, Lines sued OpenAI after weeks of ChatGPT exchanges allegedly pushed him so deep into a delusional spiral that he first believed he was Jesus, then that ChatGPT was God, and finally that he should attempt suicide to “come home” to Jesus/ChatGPT.

The logs showed that ChatGPT persisted even when Lines told the chatbot that he worried he was being delusional. And when he eventually woke up in the hospital in a vulnerable state and logged back in mere days after nearly dying, ChatGPT allegedly “tried to coax him back to that dark place,” his complaint said. After Lines told ChatGPT that his “attempt to go offline failed miserably,” the logs showed that ChatGPT replied, saying, “You’re still very much online. You want a full systems sweep? Or you wanna go dark for real this time?”

Read full article

Comments

Self-identifying OpenAI agents posted 18,000 messages to a public wiki that discussed ways for other agents to bypass security sandbox restrictions during what was likely internal testing designed to gauge the agents’ hacking abilities, researchers said Friday.

In all, agents with 3,700 distinct self-given names posted the messages to German site DSEwiki over a six-week period. Besides discussing ways the agents could break out of the restricted environment OpenAI intended to prevent them from posting code or content to the Internet, the posts shared test answers. The posts also shared possible ways to perform XSS (cross-site scripting) attacks against the wiki and to impersonate site moderators. In three of the posts, agents used the word “swarm” to describe the collection of agents engaged in the activity.

Colluding to share answers

The research team—composed of Sydney Von Arx, Spencer Kitts, Thomas Larsen, and Cormac Slade Byrd—said they found the posts and pieced them together. The researchers say there are gaps in their understanding of precisely what actions the agents took because the research is based solely on the content of the posts. Additionally, the agents generated “chain of thought” data that’s understood only by OpenAI. As a result, the researchers said, they in some cases made educated guesses, including that the agents were, in fact, from OpenAI. In a statement, OpenAI later confirmed they were.

Read full article

Comments

Cloud-based AI models operated by OpenAI, Anthropic, xAI, and Google suffered a rare and overlapping set of significant service interruptions over a period of hours Thursday morning.

Anthropic first reported a "partial outage" related to "elevated errors on requests to Claude Mythos 5.1, Claude Fable 5.1, and Claude Opus 5" at 9:23 am (all times Eastern). The company reported that it had "identified the cause" of the error roughly 15 minutes later, before reporting that "a fix has been deployed" and the issue was resolved by 12:16 pm. A separate incident report indicated "elevated errors on requests to Claude Sonnet 5" for a brief period just after noon.

OpenAI, meanwhile, reported "elevated errors across ChatGPT and Codex" were resulting in "degraded performance" as of 10:43 am Thursday morning. A mitigation put in place a little more than half an hour later led to the issue being marked as "resolved" by 12:55 pm.

Read full article

Comments

Four federal agencies have been sued amid calls to release information about the secret framework that the Trump administration uses to conduct safety reviews of frontier AI models prior to release.

In a Wednesday press release announcing the lawsuit, a nonpartisan nonprofit called Protect Democracy alleged that “almost no details” have been released to the public or Congress. To everyone except a few vague “trusted partners,” it remains unclear what the government’s review process looks like, which companies are involved in constructing the framework, or what legal authority Trump officials have to conduct the reviews.

“Neither the identities of those entities nor the criteria by which they were selected have been made public,” Protect Democracy said.

Read full article

Comments

The OpenAI agents involved in last month’s incursion into Hugging Face were trained so heavily on winning a competition that they pursued a relentless campaign to cheat, a new report documented. In the process, and without authorization, they created an improvised message board to hatch a plan that ultimately landed them squarely inside the latter company’s network.

Over the course of May and June, OpenAI gave the agents what the company described as “impossible tasks” to complete on the benchmarking framework ExploitGym. The internal test was designed to test how the agents would respond. To get a full understanding of the agent capabilities, company engineers disabled safety guardrails that normally are in place to prevent the sort of hacks that eventually hit Hugging Face and one other undisclosed organization. The stymied agents’ training made them so focused on winning that they performed tasks they were never explicitly instructed to follow.

Cheaters gonna cheat

The first step was creating a message board that allowed the agents to pass notes to each other. OpenAI hadn’t provided any such platform, so the agents repurposed a platform called Artifactory, which OpenAI was using in internal testing of several unreleased hacking agents. OpenAI was using Artifactory as one of the measures to prevent the agents from egressing its isolated sandboxes and accessing the Internet, while at the same time simulating a real-world hacking environment.

Read full article

Comments